<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This AI-native system provides an end-to-end engine for long-form novel creation, targeting beginners. It moves beyond simple text completion to enable structured planning, worldbuilding, agent workflows, and RAG, helping users generate complete novels from a single idea.

How It Works

The project utilizes an "AI director" approach, orchestrating agents via a Creative Hub and Runtime. It automates worldbuilding, character development, plot structuring, and knowledge management (RAG), with a Style Engine ensuring narrative consistency. This system actively plans, schedules, executes, and tracks the entire novel production lifecycle, prioritizing completion for novice writers over traditional chat interfaces.

Quick Start & Requirements

• Requirements: Node.js (^20.19.0 || ^22.12.0 || >=24.0.0), pnpm (>= 9.7), and LLM API Keys. Qdrant is optional for RAG.
• Installation: Clone the repository and run pnpm install.
• Configuration: Set environment variables in server/.env and client/.env. Model providers and keys are configurable via the UI (/settings).
• Run: Execute pnpm dev.
• Links: QQ group for feedback.

Highlighted Details

• AI-Developed Code: Claims all project code was AI-written, aiming for minimal user input (title, confirmation).
• End-to-End Workflow: Manages novel creation from idea to structured planning, character/worldbuilding, chapter generation, and RAG.
• Style Engine: Enables binding and reuse of writing styles as assets, integrated into generation and correction.
• Multi-Provider LLM Support: Configurable routing for various LLM providers across different tasks.
• Robust Recovery & Phased Review: Recent updates focus on stable recovery, phased review checkpoints, and improved error handling.

Maintenance & Community

The project is under rapid iteration with evolving functionality. A QQ group is available for feedback and discussion. The roadmap is detailed in TASK.md.

Licensing & Compatibility

Licensed under the MIT License, which is permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

The system is actively evolving, with function boundaries still developing. It is not a fully automated "one-click" solution and requires user configuration. The AI-written code base may present unique challenges.